WACrew

definir_modo

Set a WhatsApp chat to autonomous or confirm-before-send mode, persist the choice per chat, and optionally enable triage agent and executor.

Instructions

Define se um chat está em modo AUTÔNOMO (a IA envia sem confirmar) ou CONFIRMAR (default: a IA mostra o texto e espera OK do operador antes de enviar). Persiste por chat — você liga uma vez e vale até desligar, sem depender de re-combinar a cada msg. O responder lê esse modo. É convenção respeitada pela IA, não trava de código. Também liga o agente de triagem do chat (agente: off/issue/pr) e escolhe o executor (claude/copilot).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "grupo": "<grupo>"
    },
    "name": "definir_modo"
  }
}

Input Schema

Name	Required	Description
`grupo`	Yes	slug do grupo ou DM (de listar_grupos; DM = dm-<id>)
`typos`	No	liga/desliga typo proposital (raro, ~3%) corrigido com um balão '*palavra' — humanização; default OFF
`agente`	No	agente de triagem do chat: off (não lê), issue (cria issue e espera seu ok), pr (issue já sai marcada pro executor)
`autonomo`	No	true = IA envia direto; false = volta pro padrão 'confirmar antes'; ausente = não mexe
`executor`	No	quem executa a issue aprovada; default claude
`latencia_maxima_s`	No	teto (segundos) da latência humana das entregas desse chat; null = padrão (4 h)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden and does so well: it discloses per-chat persistence, the default mode, the default executor, that `responder` reads the flag, and critically that it is 'convenção respeitada pela IA, não trava de código' — an honesty signal an agent needs. It stops short of describing failure modes (e.g., invalid grupo) or how to fully revert the triage agent/executor settings.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core autonomy/confirm decision before the persistence note, sibling reference, caveat and secondary settings. Every sentence carries distinct information; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter, annotation-free configuration tool with no output schema, this covers the essentials: what changes, defaults, persistence and who reads the value. Minor gaps remain around required 'grupo' sourcing and what the call returns on success.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter including enums, defaults and the null-means-default latency cap is already documented in the schema; the description only restates agente (off/issue/pr) and executor (claude/copilot). No additional semantics, units or interaction rules between parameters are added beyond the structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Define se um chat está em modo AUTÔNOMO... ou CONFIRMAR') and spells out both modes, so the effect is unambiguous. It also names the sibling that consumes the setting ('O `responder` lê esse modo'), but it never contrasts itself with other chat-configuration siblings such as definir_contrato, leaving a small ambiguity about which tool owns what.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through persistence guidance ('você liga uma vez e vale até desligar, sem depender de re-combinar a cada msg') and stated defaults (CONFIRMAR default, executor default claude), which tells an agent the call is a one-time setup rather than a per-message step. It does not say when an agent should prefer this over alternatives or what conditions argue against switching to autonomous mode.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.